Apple M1 Microarchitecture Research by Dougall Johnson

Firestorm: Overview | Base Instructions | SIMD and FP Instructions
Icestorm:  Overview | Base Instructions | SIMD and FP Instructions

FRSQRTE (vector, 2S)

Test 1: uops

Code:

  frsqrte v0.2s, v0.2s
  movi v0.16b, 1
  movi v1.16b, 2

(no loop instructions)

1000 unrolls and 1 iteration

Retires: 1.000

Issues: 1.000

Integer unit issues: 0.000

Load/store unit issues: 0.000

SIMD/FP unit issues: 1.000

retire (01)cycle (02)031e3f4e51inst issue (52)~issue fp/simd (54)~dispatch fp/simd (57)huge thing fp/simd (5b)696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op fp/simd (7e)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst neon or fp (9a)a8accfd5d6ddinst fetch restart (de)e0? fp/simd (ee)f5f6f7f8fd
100430372215611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
10043037220611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372390611900251000100010001044513018303730372738328951000100010003037303711100110003373116112919100030383038303830383038
10043037230611900251000100010001044513018303730372738328951000100010003037303711100110001073116112918100030383038303830383038
10043037220611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372318611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
10043037220611900251000100010421044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
10043037220611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
10043037230611900251000100010001044513018303730372738328951000100010003037303711100110000073116112919100030383038303830383038
100430372206119002510001000100010445130183037303727383289510001000100030373037111001100018075116112919100030383038303830383038

Test 2: Latency 1->2

Code:

  frsqrte v0.2s, v0.2s
  movi v0.16b, 1
  movi v1.16b, 2

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)031e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa1a8a9acc2cfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
1020430037225015619900251010010010000100100005001067451030018300373003728588328745101682001000020010000300373003711102011009910010010000100010007101161129919100001003003830038300383003830038
102043003722506119900251010010010000100100005001067451030018300373003728588328745101002001000020010000300843003711102011009910010010000100000007101161129919100001003003830038300383003830038
102043003722506119900251010010010000100100005001067451030018300373003728588328745101002001000020010000300373003711102011009910010010000100000007101161129919100001003003830038300383003830038
102043003722506119900251010010010000100100005001067451130018300373003728588328745101002001000020010000300373003711102011009910010010000100000007101161129919100001003003830038300383003830038
102043003722508219852251010010210000100100426101067451030018300373003728588328745101002001000020010000300373003711102011009910010010000100010007101161129919100001003003830038300383003830038
1020430037224025119900251010010010000100100005001067451030018300373003728588328745101002001000020010000300373003711102011009910010010000100000007101161129919100001003003830038300383003830038
102043003722506119900251010010010000100100005001067451130018300373003728588328745101002001000020010000300373003711102011009910010010000100212128307421162129919100001003003830038300853003830038
1020430037225010319900251010010010000100100005001067451030018300373003728588328745101002001000020010000300373003711102011009910010010000100010007101161129919100001003003830038300383003830038
102043003722506119900251010010010000100100005001067451030018300373003728588328745101002001000020010000300373003711102011009910010010000100000007101161129919100001003003830038300383003830038
102043003722506119900251010010010000100100005001067451130162300373003728588328745101002001000020010000300373003711102011009910010010000100010007101161129919100001003003830038300383003830038

1000 unrolls and 10 iterations

Result (median cycles for code): 3.0037

retire (01)cycle (02)030918191e3f4e51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acc2cdcfd5d6ddinst fetch restart (de)e0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
100243003722400006119900251001010100001010000501067451030018300373003728610328767100102010000201000030037300371110021109101010000100000640316332991910000103003830038300383003830038
100243003722500006119900251001010100001010000501067451030018300373003728610328767100102010000201000030037300371110021109101010000100000640316332991910000103003830038300383003830038
100243003722400006119900251001010100001010000501067451130018300373003728610328767100102010000201006830037300371110021109101010000100000640316332991910000103003830038300383003830038
100243003722500006119900251001010100001010000501067451130018300373003728610328767100102010000201000030037300371110021109101010000100000640316332991910000103003830038300383003830038
100243003722500006119900251001010100001010000501067451030018300373003728610328767100102010000201000030037300371110021109101010000100000640316332991910000103003830038300383003830038
100243003722500006119900251001010100001010000501067451130018300373003728610328767100102010000201000030037300371110021109101010000100000640316332991910000103003830038300383003830038
100243003722500006119900251001010100001010000501067451130018300373003728610328767100102010000201000030037300371110021109101010000100000640316332991910000103003830038300383003830038
100243003722500006119900251001010100001010000501067451030018300373003728610328767100102010000201000030037300371110021109101010000100000640316332991910000103003830038300383003830038
100243003722500006119900251001010100001010000501067451030018300373003728610328767100102010000201000030037300371110021109101010000100000640316332991910000103003830038300383003830038
100243003722500006119900251001010100001010000501067451030018300373003728610328767100102010000201000030037300371110021109101010000100000640316332991910000103003830038300383003830038

Test 3: throughput

Count: 8

Code:

  frsqrte v0.2s, v8.2s
  frsqrte v1.2s, v8.2s
  frsqrte v2.2s, v8.2s
  frsqrte v3.2s, v8.2s
  frsqrte v4.2s, v8.2s
  frsqrte v5.2s, v8.2s
  frsqrte v6.2s, v8.2s
  frsqrte v7.2s, v8.2s
  movi v8.16b, 9

(fused SUBS/B.cc loop)

100 unrolls and 100 iterations

Result (median cycles for code divided by count): 1.0005

retire (01)cycle (02)031e1f3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)60696d6edispatch stall (70)72scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acc5branch mispredict (cb)cdcfd5d6dde0? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80205800405999039258010010080000100800005006400000800208013680039699710669993801002008000820080008800398003911802011009910010080000100001115117016080036800001008004080040800408004080040
80204800396000039258010010080000100800005006400000800208003980039699710669993801002008000820080008800398003911802011009910010080000100001115117016080036800001008004080040800408004080040
802048003960000324258010010080000100800005006400001800208003980039699710669993801002008000820080008800398003911802011009910010080000100001115117016080036800001008004080040800408004080040
802048003959900725258010010080000100800005006400000800208003980039699710669993801002008000820080008800398003911802011009910010080000100001115117016080036800001008004080040800408004080040
802048003959900704258010010080000100800005006400000800208003980039699710669993801002008000820080008800398003911802011009910010080000100001115117016080036800001008004080040800408004080040
802048003959900704258010010080000100800005006400000800208003980039699710669993801002008000820080008800398003911802011009910010080000100001115117016080036800001008004080040800408004080040
80204800395990039258010010080000100800005006400000800208003980039699710669993801002008000820080008800398003911802011009910010080000100001115117016080036800001008004080040800408004080040
802048003960000704258010010080000100800005006400000800208003980039699710669993801002008000820080008800398003911802011009910010080000100001115117016080036800001008004080040800408004080040
80204800395990039258010010080000100800005006400000800208003980039699710669993801002008000820080008800398003911802011009910010080000100001115117016080036800001008004080040800408004080040
80204800396000039258010010080000100800005006400000800208003980039699710670024801262008000820080008800398003911802011009910010080000100061115117016080036800001008004080040800408004080040

1000 unrolls and 10 iterations

Result (median cycles for code divided by count): 1.0005

retire (01)cycle (02)03090e181e1f3f51inst issue (52)~issue int (53)~issue fp/simd (54)~dispatch int (56)~dispatch fp/simd (57)huge thing int (59)huge thing fp/simd (5b)5f6061696d6edispatch stall (70)72scheduler rewind (75)scheduler stall (76)~dispatch op (78)~map op int (7c)~map op fp/simd (7e)~map lookup int (7f)~map lookup fp/simd (81)8283pipeline redirect (84)85inst all (8c)inst branch (8d)inst branch taken (90)inst b.cc (94)inst integer (97)inst neon or fp (9a)9fa8acc5cfd0d2d5d6ddinst fetch restart (de)e0ea? fp/simd (ee)gpr retires (ef)f5f6f7f8fd
80024800396000200050258001010800001080000506400000158002080039800396998603700198001020800002080000800898003911800211091010800001000050200022169680034080000108004080040800408008980040
8002480039599000120922580010108000010800005064000000080020800398003969986037001980062208000020800008003980039118002110910108000010023680502000145610580185080000108004080040800408004080040
800248003959910117410871510080058108002410800785064020300080020800398003970005017702028008820800002080000800398003911800211091010800001020050205293281080034080000108004080040800408004080040
8002480039599000007572580010108000010800005064000000080020800398003969986037001980010208011020800418003980039118002110910108000010000502050151611880034080000108004080040800408004080040
800248003959900000715258001010800001080000506400000008002080039800396998603700198001020800002080000800398003911800211091010800001000050200012164880034080000108004080040800408004080040
80024800395990000071525800101080000108000050640000010800208003980039699860370019800102080000208000080039800391180021109101080000100005020005167580034080000108004080040800408004080040
80024800395990000071525800101080000108000050640000000800208003980039699860370019800102080000208000080039800391180021109101080000100005020528168880034080000108004080040800408004080040
8002480039599000005025800101080000108000050640000000800208003980039699860370019800102080000208000080039800391180021109101080000100005020008167480034080000108004080040800408004080040
8002480039599000005025800101080000108000050640000000800208003980039699860370019800102080000208000080039800391180021109101080000100005020528169880034080000108004080089800408004080087
800248003960000000502580010108000010800005064000000080020800398003969986037001980010208000020800008008880039118002110910108000010015050200061661080034080000108004080040800408004080040